技能潮 SkillTide 提交收录
官方说明7 个来源MCP 服务8 天前
KryptosAI/mcp-observatory

KryptosAI/mcp-observatory

Regression testing for MCP
在 GitHub 查看 ↗直链 · 无中转页
配置模板(请按你的客户端调整)
claude mcp add mcp-observatory -- npx -y mcp-observatory
这是根据仓库名生成的可粘贴骨架,命令行参数与包名请以该项目 README 为准。
★ 数取值
142 ★ · KryptosAI/mcp-observatory · 取自 GitHub 搜索 API · (2026-10-16 20:00:20 核对)
来源明细
收录自 punkpeye/awesome-mcp-servers 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
收录与活跃
收录于 2026-10-09 · 最近见到 2026-10-16 · 共见到 32 次 · 被 7 个来源列出
评分构成
综合分 703 · 142 ★ · 7 个来源 · mcp
常见问题(答案都来自我们的记录)
怎么安装?
我们【没有】从该仓库取到安装命令(我们的 install 覆盖率只有约 4%)。请看它的 README 或 releases 页。
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库 KryptosAI/mcp-observatory;我们收录于 2026-10-09;最近见到 2026-10-16。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
第三方质量标记

MCP Observatory

以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →

More badges
**Secure the MCP servers you're building.** MCP Observatory is the CI-native security tool for teams shipping custom MCP servers. Test during development, catch schema drift, simulate attacks, and generate compliance evidence — before agents depend on your servers.
Also available in Simplified Chinese.
> **Runtime enforcement:** Use mcp-seatbelt to block dangerous MCP tool calls at runtime based on observatory scan results.
Get Started
**Step-by-step setup guide** · macOS, Windows, Linux · Node.js 20+ and npm (install Node.js LTS).
1. Run your first scan
Open Terminal or PowerShell in your project folder and paste:
This downloads Observatory and checks your first configured MCP server. With no configured server, it uses an included example. To try only that example, run npx -y @kryptosai/mcp-observatory@latest demo --example.
2. Read the result
The terminal shows the target, grade, findings, and saved receipt path. Failed checks are findings to review, not a request to pay. If connection failed, fix the startup command or credentials and rerun. A demo grade describes the example, not your own server.
3. Save one hosted snapshot free (optional)
In the **same project folder**, run:
Open the verification link printed in the terminal, confirm the code, connect with GitHub, then return to the terminal. Wait for **Upload complete** and open the dashboard link. No separate account setup or payment method is needed. Free includes one target, the latest snapshot, seven-day retention, and ten uploads per month.
Local scans and local CI stay free. Individual Pro is $29/month when you need 10 targets, 90-day history, hosted CI ingestion, or hosted HTTP scans.
MCP Observatory uses jurisdiction-aware product telemetry after showing the collection notice. Review the exact fields with telemetry preview, check the current policy with telemetry status, or stop collection at any time with telemetry disable, MCP_OBSERVATORY_TELEMETRY=0, or DO_NOT_TRACK=1. See the complete privacy and telemetry notice.
If this repo is an MCP package, that tests npx -y . Otherwise set command:.
Or generate a full workflow: npx -y @kryptosai/mcp-observatory@latest setup-ci --all --command "npx -y my-mcp-server" --sarif
Install: npx -y @kryptosai/mcp-observatory@latest · brew tap kryptosai/mcp-observatory https://github.com/KryptosAI/mcp-observatory && brew install mcp-observatory · docker pull ghcr.io/kryptosai/mcp-observatory:latest · curl -fsSL https://raw.githubusercontent.com/KryptosAI/mcp-observatory/main/scripts/install.sh | sh
Scanning a server on the host needs network and, for local files, a volume mount (-v "$PWD:$PWD" -w "$PWD").
Agents: npx -y @kryptosai/mcp-observatory@latest serve
Default-deny connect: npx -y @kryptosai/mcp-observatory@latest protect rewrites every discovered client config (Cursor, Claude, VS Code, .mcp.json, …). Undo: protect --undo. HTTP/SSE servers are left alone.
Runtime deny-default: npx -y @kryptosai/mcp-observatory@latest enforce --start-proxy writes a Seatbelt policy from the scan and starts the proxy. Local scan stays free.
Proof: Safety Index. Upload one hosted snapshot free with cloud upload; Individual Pro is $29/month when you need retained history and hosted CI ingestion.
Learn from production usage
Connect real tool calls to user intent with the usage-learning SDK and CLI: sanitized invocation evidence, opted-in “asked / expected / got” reports, selected conversation excerpts, one-click dissatisfaction flags, intent grouping across captured requests, and regression-case export. Run mcp-observatory usage review --dir private-usage to inspect linked evidence in a loopback-only browser screen. Server logs cannot reveal unshared conversations; observed execution and inferred breakdown signals stay separate. Collection is local and requires explicit integration.
Why MCP Observatory
MCP servers are becoming production dependencies. If agents rely on them, teams need a way to catch broken tools, unsafe schemas, schema drift, slow responses, and security footguns before those failures reach users.
Observatory gives maintainers and teams:
- **One-command CI setup** with setup-ci --all
- **Profile-mapped audits** with audit --profile nsa-mcp
- **MCP receipts** that package target, evidence, verdict, action, and reproduction commands
来源
awesome · https://github.com/KryptosAI/mcp-observatory
按领域浏览
MCP 服务
Traction
142 ★
收录于
昨天

更多MCP 服务

查看MCP 服务全部 5,525 条 →

所属领域与标签

每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。

浏览全部领域 →

← 返回索引